© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 18375
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Dem"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.92
    ties
    -0.77
    glers
    -0.75
    =~=~
    -0.71
    olkien
    -0.71
    DAY
    -0.69
    FFFF
    -0.68
    APTER
    -0.67
    Pull
    -0.67
     Carbuncle
    -0.67
    POSITIVE LOGITS
    olition
    1.08
    agogue
    0.87
    ecast
    0.82
     Dem
    0.82
    psey
    0.80
    agog
    0.79
    onym
    0.78
     unden
    0.77
    ethy
    0.75
    ository
    0.75
    Activations Density 0.005%

    No Known Activations